content-repurposing
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of natural language instructions for an AI agent. It does not include any shell commands, scripts, or binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting external data (links, transcripts, and drafts) which is an untrusted input source. However, the skill lacks any dangerous capabilities (such as network access, file system writes, or subprocess execution) that could be leveraged if malicious instructions were present in that data.
- Ingestion points: Step 1 (SKILL.md) gathers links, transcripts, and drafts from the user.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the source content.
- Capability inventory: No tools, scripts, or system commands are referenced or required for execution.
- Sanitization: No input sanitization or validation is described.
Audit Metadata